© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5076
    Prev
    Next
    INDEX
    Explanations

    phrases related to educational and political discourse

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    394
    +0.27
    1.1%
    1842
    +0.23
    0.9%
    1967
    +0.17
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1129
    +0.27
    0.25
    394
    +0.23
    0.17
    599
    +0.17
    0.22
    Negative Logits
     lidl
    -0.94
     riviera
    -0.88
     peppa
    -0.87
     CiNii
    -0.83
     madonna
    -0.83
     lamborghini
    -0.82
     vespa
    -0.82
     inconce
    -0.82
     affez
    -0.80
     milf
    -0.80
    POSITIVE LOGITS
    </i>
    0.56
    </em>
    0.54
     [
    0.48
    [
    0.46
    …
    0.45
     [...]
    0.45
     …
    0.44
    ...
    0.42
     ...
    0.42
    ”
    0.42
    Activations Density 9.582%

    No Known Activations